|
|
@@ -17,21 +17,19 @@ pip install -q git+https://github.com/huggingface/peft.git
|
|
|
|
|
|
2. [Install bitsandbytes from source](https://github.com/TimDettmers/bitsandbytes/blob/main/compile_from_source.md)
|
|
|
|
|
|
-
|
|
|
### Inference
|
|
|
|
|
|
See `generate.py`. This file reads the `decapoda-research/llama-7b-hf` model from the Huggingface model hub and the LoRA weights from `tloen/alpaca-lora-7b`, and runs inference on a specified input. Users should treat this as example code for the use of the model, and modify it as needed.
|
|
|
|
|
|
-
|
|
|
### Training
|
|
|
|
|
|
Under construction.
|
|
|
|
|
|
-
|
|
|
### To do
|
|
|
|
|
|
- [ ] Hyperparameter tuning
|
|
|
- [ ] Documentation for notebook
|
|
|
- [ ] Support for `13b`, `30b`, `65b`
|
|
|
+- [ ] Train a version that doesn't waste tokens on the prompt header
|
|
|
- [ ] Inference CLI and evaluation
|
|
|
- [ ] Better disclaimers about why using LLaMA without permission is very bad!
|
Eric Wang